{
  "schema_version": "openagent.resource.v1",
  "id": "res_browser_use",
  "slug": "browser-use",
  "status": "published",
  "identity": {
    "name": "browser-use",
    "one_liner": "Open-source browser automation agent framework that makes websites accessible to AI agents.",
    "short_description": "browser-use is an MIT-licensed Python project for connecting AI agents to browser actions, making it useful for teams prototyping web automation, browser agents, and task execution over real websites."
  },
  "classification": {
    "resource_type": "agent",
    "primary_category": "agents",
    "subcategories": [
      "browser-automation",
      "browser",
      "workflow-orchestration",
      "tool-calling",
      "self-hosted"
    ]
  },
  "positioning": {
    "why_it_matters": "browser-use matters because browser control is one of the most practical surfaces for action agents. Many workflows still happen inside websites, and this project gives builders a focused open-source framework for testing that layer.",
    "best_for": [
      "Developers building agents that need to operate websites",
      "Teams prototyping browser automation before committing to a larger agent platform",
      "Researchers evaluating web task completion and browser action safety"
    ],
    "not_for": [
      "Users who want a complete no-code automation product",
      "Teams that cannot manage credentials, browser sessions, and site-specific failure cases"
    ],
    "use_cases": [
      "browser-agent",
      "self-hosted-ai",
      "developer-workflow"
    ],
    "target_audience": [
      "developer",
      "agent_builder"
    ],
    "maturity": "active"
  },
  "decision_signals": {
    "deployment_modes": [
      "self_hosted",
      "cloud"
    ],
    "open_source": true,
    "local_first": false,
    "self_hostable": true,
    "has_api": false,
    "has_gui": false,
    "supports_mcp": false,
    "supports_docker": false
  },
  "facts": {
    "license": "MIT",
    "pricing_model": "open_source",
    "github_stars": 88493,
    "github_forks": 10154,
    "github_repo_full_name": "browser-use/browser-use",
    "last_verified_at": "2026-04-19"
  },
  "capabilities": {
    "core_capabilities": [
      "browser-automation",
      "browser",
      "workflow-orchestration",
      "tool-calling"
    ],
    "interfaces": [
      "repo",
      "docs"
    ]
  },
  "links": {
    "primary_url": "https://github.com/browser-use/browser-use",
    "items": [
      {
        "type": "github",
        "label": "GitHub",
        "url": "https://github.com/browser-use/browser-use"
      },
      {
        "type": "homepage",
        "label": "Homepage",
        "url": "https://browser-use.com"
      },
      {
        "type": "docs",
        "label": "Docs",
        "url": "https://docs.browser-use.com/"
      }
    ]
  },
  "media": {
    "thumbnail_brief": {
      "resource_type": "agent",
      "visual_motif": "browser window outline with action path nodes and a small pointer trail",
      "background_style": "clean editorial surface with restrained green and blue accents",
      "title_overlay": "browser-use",
      "subtitle": "Websites for AI agents",
      "avoid": [
        "literal browser screenshots with private data",
        "cartoon robot hands",
        "busy automation flowchart"
      ]
    }
  },
  "tags": {
    "category": [
      "agent",
      "open-source"
    ],
    "capability": [
      "browser-automation",
      "browser",
      "workflow-orchestration",
      "tool-calling"
    ],
    "constraint": [
      "open-source",
      "self-hosted"
    ],
    "scenario": [
      "browser-agent",
      "self-hosted-ai",
      "developer-workflow"
    ]
  },
  "relationships": {},
  "machine_readable": {
    "canonical_url": "https://www.openagent.bot/agents/browser-use",
    "json_url": "https://www.openagent.bot/agents/browser-use.json",
    "markdown_url": "https://www.openagent.bot/agents/browser-use.md"
  },
  "seo": {
    "title": "browser-use: Open-source browser automation for AI agents",
    "description": "browser-use profile: what the open-source browser agent framework is, when to use it, official links, command line, and OpenAgent structured data."
  },
  "editorial": {
    "featured_reason": "A focused open-source browser agent framework that pairs well with OpenClaw-style action-agent workflows.",
    "trust_note": "Verified from source links and project metadata.",
    "core_strengths": [
      {
        "title": "Browser-first agent surface",
        "description": "browser-use focuses on making websites actionable for AI agents.",
        "why_it_matters": "Most business workflows still cross web apps, forms, dashboards, and authenticated pages."
      },
      {
        "title": "Python developer workflow",
        "description": "The project is built for developers who want to compose browser automation into agent code.",
        "why_it_matters": "A focused framework can be easier to adopt than a full agent operating environment."
      },
      {
        "title": "Strong fit for narrow automation tests",
        "description": "It is useful for validating whether a browser task can be represented as an agent workflow.",
        "why_it_matters": "Narrow tests reveal site failures, credential needs, and reliability issues before a team scales automation."
      }
    ],
    "use_case_notes": [
      {
        "title": "Website task automation",
        "description": "Use browser-use when an agent needs to navigate, click, type, inspect pages, or complete a web flow."
      },
      {
        "title": "Browser agent prototypes",
        "description": "Test browser automation as a standalone layer before adding memory, scheduling, or full workflow orchestration."
      },
      {
        "title": "Web QA and research workflows",
        "description": "Evaluate how agents behave across real web pages, changing layouts, and multi-step browser tasks."
      }
    ],
    "compare_notes": [
      {
        "title": "Choose browser-use for browser automation primitives",
        "summary": "OpenClaw and OpenHands cover broader agent workflows. browser-use is more focused when the core problem is browser operation itself.",
        "against": "full action-agent platforms"
      }
    ],
    "getting_started": [
      {
        "label": "Open the GitHub repository",
        "url": "https://github.com/browser-use/browser-use",
        "type": "github"
      },
      {
        "label": "Read the documentation",
        "url": "https://docs.browser-use.com/",
        "type": "docs"
      },
      {
        "label": "Visit the project website",
        "url": "https://browser-use.com",
        "type": "homepage"
      }
    ],
    "command_line": [
      {
        "label": "Install browser-use",
        "command": "pip install browser-use",
        "description": "Use the official package path, then follow the docs for model provider and browser setup."
      }
    ],
    "seo_article": {
      "intro": "browser-use is one of the most direct ways to test whether an AI agent can operate a website. Instead of starting with a broad agent platform, it focuses on the browser surface: navigation, actions, page state, and the messy reality of web workflows.",
      "what_it_is": "browser-use is an open-source Python framework that makes websites accessible to AI agents. It gives developers a way to connect model decisions to browser actions so agents can interact with web pages rather than only describe what a user should do.",
      "why_it_matters": "If action agents are going to be useful, they need to work where real work happens. Browser-based systems are still the front door to many tools, CRMs, dashboards, stores, and internal apps. browser-use is useful because it isolates that problem and lets teams test it directly.",
      "how_it_works": "A typical experiment starts with a narrow browser task, a model provider, and a controlled browser session. The developer then observes how the agent reads page state, selects actions, handles errors, and recovers when a page changes.",
      "use_cases": [
        {
          "title": "Automating web research",
          "description": "Use browser-use to test agents that collect information from pages, compare options, or navigate repeated research flows."
        },
        {
          "title": "Form and dashboard workflows",
          "description": "Evaluate whether an agent can complete repeatable web tasks that previously required manual clicking."
        },
        {
          "title": "Browser-agent safety testing",
          "description": "Use it to study what permissions, prompts, and guardrails are needed when an agent controls a browser."
        }
      ],
      "alternatives": [
        {
          "title": "Use OpenClaw when you need a broader action-agent workspace",
          "summary": "browser-use is focused on browser automation. OpenClaw is more relevant when browser control is only one layer in a larger workflow runtime.",
          "against": "OpenClaw"
        }
      ],
      "getting_started": [
        {
          "label": "Start with the docs",
          "url": "https://docs.browser-use.com/",
          "type": "docs"
        },
        {
          "label": "Inspect the repository",
          "url": "https://github.com/browser-use/browser-use",
          "type": "github"
        }
      ],
      "faq": [
        {
          "question": "Is browser-use open source?",
          "answer": "The GitHub repository is listed with an MIT license."
        },
        {
          "question": "Is browser-use the same as a full agent platform?",
          "answer": "No. It is more focused on browser automation. You may still need memory, scheduling, permissions, and workflow orchestration around it."
        },
        {
          "question": "Who should try browser-use?",
          "answer": "Developers who need to test whether web tasks can be represented as reliable AI agent workflows should start here."
        }
      ]
    }
  },
  "timestamps": {
    "created_at": "2026-04-19T00:00:00.000Z",
    "updated_at": "2026-04-19T00:00:00.000Z",
    "published_at": "2026-04-19T00:00:00.000Z"
  }
}